AI News

⚡ 9 minutes ago
1
1
\texttt{Range-Arithmetic}: Verifiable Deep Learning Inference on an Untrusted Party (arxiv.org)
2
1
TileFuse: A Fused Mixed-Precision Kernel Library for Efficient Quantized LLM Inference on AMD NPUs (arxiv.org)
3
1
When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranking Pipelines (arxiv.org)
4
1
OmniBioTwin: A System-of-Twinned-Systems Framework for Health Digital Twins (arxiv.org)
5
1
RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark (arxiv.org)
6
1
SPEAR: A System for Post-Quantization Error-Adaptive Recovery Enabling Efficient Low-Bit LLM Serving (arxiv.org)
7
1
Artificial Intelligence in Ship Finance: Applications, Opportunities, and a Case Study in AI-Augmented Loan Origination (arxiv.org)
8
1
Learning to Inject: Automated Prompt Injection via Reinforcement Learning (arxiv.org)
9
1
Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery (arxiv.org)
10
1
AI4SLT: Empirical Processes in Lean 4 for Formal Statistical Learning Theory (arxiv.org)
11
1
Prediction-Powered Risk Monitoring of Deployed Models for Detecting Harmful Distribution Shifts (arxiv.org)
12
1
Open Materials Generation with Inference-Time Reinforcement Learning (arxiv.org)
13
1
Towards a Bridge Layer Between Bibliographic and Formalized Mathematical Knowledge (arxiv.org)
14
1
Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents (arxiv.org)
15
1
An Ethical eValuation Agent (EeVA): Results of a Proof-of-Concept Test on a Prototype Agentic-like Workflow to Assist Ethical Deliberations (arxiv.org)
16
1
Preregistration for Experiments with AI Agents (arxiv.org)
17
1
The Environmental Cost of LLMs in AIED: Reporting and Practices (arxiv.org)
18
1
From Awareness to Action: Understanding and Overcoming the Research-Practice Gap in Algorithmic Fairness for Public Health (arxiv.org)
19
1
FOCUS: DLLMs Know How to Tame Their Compute Bound (arxiv.org)
20
1
Robust Privacy: Inference-Stage Privacy through Certified Robustness (arxiv.org)
21
1
Robustness of Mixtures of Experts to Feature Noise (arxiv.org)
22
1
Analytic Bijections for Smooth and Interpretable Normalizing Flows (arxiv.org)
23
1
Learning Object Manipulation from Scratch via Contrastive Interaction (arxiv.org)
24
1
Every Act Has Its Price: Compressed Moral Composition in Frontier LLMs (arxiv.org)
25
1
T2MM: An LLM Supported Architecture For Inquiry-Based Modeling (arxiv.org)
26
1
BioDivergence: A Benchmark and Evaluation Framework for Hidden Contextual Contradictions in Biomedical Abstracts (arxiv.org)
27
1
What Limits Does Quantization Place on Dense Top-$k$ Retrieval? A Theoretical Study (arxiv.org)
28
1
Unifying Learning Dynamics and Generalization in Transformers Scaling Law (arxiv.org)
29
1
Improving Generalization and Data Efficiency with Diffusion in Offline Multi-agent RL (arxiv.org)
30
1
Towards Deep Learning Surrogate for the Forward Problem in Electrocardiology: A Scalable Alternative to Physics-Based Models (arxiv.org)
31
1
Semantic search for 100M+ galaxy images using AI-generated captions (arxiv.org)
32
1
Irresponsible AI: big tech's influence on AI research and associated impacts (arxiv.org)
33
1
Grounding Computer Use Agents on Human Demonstrations (arxiv.org)
34
1
FlexiBrain: Resolution-Agnostic Voxel-Level Encoding for Native fMRI (arxiv.org)
35
1
Parameter-Efficient Adapter Tuning for Tabular-Image Multimodal Learning (arxiv.org)
36
1
Evaluating and Combating the Impact of Concept Drift on the Performance of Machine Learning-Based Phishing Detection Systems (arxiv.org)
37
1
Density estimation for Hellinger via minimum-distance estimators: mixtures of Gaussians, log-concave, and more (arxiv.org)
38
1
APEX: Automated Prompt Engineering eXpert with Dynamic Data Selection (arxiv.org)
39
1
Moving Beyond Diffusion: Hierarchy-to-Hierarchy Autoregression for fMRI-to-Image Reconstruction (arxiv.org)
40
1
Certifiable Safe RLHF: Semantic Grounding and Fixed Penalty Constraint Optimization for Safer LLM Alignment (arxiv.org)
41
1
Noise-Guided Transport for Imitation Learning (arxiv.org)
42
1
Geometric Metrics and LLMs: What They Measure and When They Work (arxiv.org)
43
1
Toward Preference-aligned Large Language Models via Residual-based Model Steering (arxiv.org)
44
1
Spatially Masked Regression Reveals Local and Distributed Predictability in Electrophysiological Recordings (arxiv.org)
45
1
A Scalable PyTorch Abstraction for Multi-GPU Gaussian Splatting (arxiv.org)
46
1
Small Experiments, Cheaper Decisions: A Case Study in Staged Promotion for Micro-Pretraining (arxiv.org)
47
1
When Probing Accuracy Saturates, Fragility Resolves: A Complementary Metric for LLM Pre-Training Analysis (arxiv.org)
48
1
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models (arxiv.org)
49
1
Rule Taxonomy and Evolution in AI IDEs: A Mining and Survey Study (arxiv.org)
50
1
Adapting Prithvi-EO for Fallow Detection for Food-Water Nexus: ViT-Adapter Necks and Parameter-Efficient Backbone tuning of Geospatial Foundation Model (arxiv.org)